# SETUP: We will need tidyverse for almost all of these functions

library(tidyverse)

# ==============================================================================

# USECASE: Re-capitalize strings

x <- c("R4SS: Introduction to R for Social Scientists")

str_to_lower(x)

str_to_upper(x)

str_to_sentence(x)

str_to_title(x)

# ==============================================================================

# USECASE: Extract subsets of strings

x <- c("Apple", "Banana", "Pear")

str_sub(x, start = 1, end = 3)

str_sub(x, start = -3, end = -1)

str_sub(x, start = 2, end = -2)

str_sub(x, start = 1, end = 5) # can go beyond the end

# ==============================================================================

# USECASE: Remove whitespace from strings

x <- "  Sometimes strings have   too   much white space "
x

str_trim(x) # remove white space at the start and end

str_squish(x) # trim and then collapse inner white space

# ==============================================================================

# USECASE: Remove and replace patterns in strings

x <- "Scientists very often utilize very fancy words,
      even when they could utilize simpler ones."

str_remove(x, pattern = "very ") # removes first pattern match only

str_remove_all(x, pattern = "very ") # removes all pattern matches

str_replace(x, pattern = "utilize", replacement = "use")

str_replace_all(x, pattern = "utilize", replacement = "use")

# NOTE: More complex patterns can be found using regular expressions (regex)

# ==============================================================================

# USECASE: Create a string manipulation pipeline

x_clean <-
  x |>
  str_remove_all("very ") |>
  str_replace_all("utilize", "use") |>
  print()

# SETUP: We will need tidyverse for almost all of these functions

library(tidyverse)

# ==============================================================================

# USECASE: Determining whether someone can vote in the US

age <- 12

age_group <-
  if_else(
    condition = age >= 18,
    true = "adult",
    false = "child"
  ) |>
  print()

# ==============================================================================

# TIP: Because argument names are optional, we can shorten this (if we want)

age_group <- if_else(age >= 18, "adult", "child") |> print()

# ==============================================================================

# LESSON: This function is particularly useful applied to vectors

ages <- c(13, 18, 14, 19, 22, 16)

age_groups <- if_else(ages >= 18, "adult", "child") |> print()

# ==============================================================================

# USECASE: We can therefore use it during data wrangling

cereal <- read_csv("cereal.csv", na = "-999")

cereal2 <- mutate(cereal, popular = if_else(rating > 50, "yes", "no"))
cereal2

cereal3 <-
  cereal |>
  mutate(
    diabetes = if_else(
      condition = sugars == 0,
      true = "sugar-free",
      false = "contains sugar"
    )
  ) |>
  print()

# SETUP: We will need tidyverse for almost all of these functions

library(tidyverse)

# ==============================================================================

# USECASE: Determine what types of movies your kids can watch

ages <- c(11, 13, 18)

movies_allowed <-
  case_when(
    ages >= 17 ~ "R",
    ages >= 13 ~ "PG-13",
    ages < 13 ~ "PG"
  ) |>
  print()

# ==============================================================================

# PITFALL: Don't put the least restrictive condition first

age <- 18

movies_allowed2 <-
  case_when(
    age < 13 ~ "PG",
    age >= 13 ~ "PG-13",
    age >= 17 ~ "R"
  ) |>
  print() # age >= 13, so PG-13 wins before checking if age >= 17

# ==============================================================================

# USECASE: Use case_when to re-code variables during data wrangling

starwars

sw <-
  starwars |>
  mutate(
    species3 = case_when(
      species == "Human" ~ "Human",
      species == "Droid" ~ "Droid",
      species != "Human" & species != "Droid" ~ "Alien"
    )
  ) |>
  select(name, species3) |>
  print()

# ==============================================================================

# TIP: The next version of case_when() will add the .default argument
# This is where the elevator will drop you off if you hit no buttons

sw <-
  starwars |>
  mutate(
    species3 = case_when(
      species == "Human" ~ "Human",
      species == "Droid" ~ "Droid",
      .default = "Alien"
    )
  ) |>
  select(name, species3) |>
  print()

# NOTE: The above code won't work now, but it should in a few weeks/months
# For now, you can use TRUE ~ "Alien" and it works but is harder to explain

# SETUP: We will need tidyverse and an example dataset (from workshop website)

library(tidyverse)

gradebook <- 
  read_csv("gradebook.csv") |> 
  print()

# ==============================================================================

# USECASE: We can pivot to long format by creating name and value variables

gradebook2 <- 
  gradebook |> 
  pivot_longer(
    cols = c(test1, test2, test3, test4, test5), 
    names_to = "test", 
    values_to = "grade"
  ) |> 
  print()

# ==============================================================================

# TIP: Use selection helpers to select columns quickly

gradebook2 <- 
  gradebook |> 
  pivot_longer(
    cols = test1:test5, 
    names_to = "test", 
    values_to = "grade"
  ) |> 
  print()

# ==============================================================================

# LESSON: Automatically remove the name prefix

gradebook2 <- 
  gradebook|> 
  pivot_longer(
    cols = starts_with("test"), 
    names_to = "test", 
    values_to = "grade",
    names_prefix = "test"
  ) |> 
  print()

# SETUP: We will need tidyverse and an example dataset (from workshop website)

library(tidyverse)

diary <- read_csv("diary.csv") |> print()

# ==============================================================================

# USECASE: Reshape this long format to a wider format

diary_scale <- 
  diary |> 
  pivot_wider(
    names_from = "scale",
    values_from = "score"
  ) |> 
  print()

diary_day <- 
  diary |>  
  pivot_wider(
    names_from = "day",
    values_from = "score"
  ) |> 
  print()

# NOTE: There are thus multiple possible wide formats (for different uses)

# ==============================================================================

# LESSON: We can add a prefix to each name to avoid numeric names

diary_data

diary_day <- 
  diary |> 
  pivot_wider(
    names_from = "day",
    values_from = "score",
    names_prefix = "day_"
  ) |> 
  print()

# ==============================================================================

# LESSON: We can also pivot on multiple columns at once

diary_double <- 
  diary |> 
  pivot_wider(
    names_from = c("scale", "day"),
    values_from = "score"
  ) |> 
  print()

# SETUP: We will need tidyverse and an example dataset

library(tidyverse)

starwars

# ==============================================================================

# USECASE: Applying the same mutation to multiple variables is a pain

sw <- 
  starwars |> 
  mutate(
    hair_color = factor(hair_color),
    skin_color = factor(skin_color),
    eye_color = factor(eye_color)
  ) |> 
  print() # before

sw <- 
  starwars |> 
  mutate(
    across(
      .cols = c(hair_color, skin_color, eye_color), 
      .fns = factor
    )
  ) |> 
  print() #after

# ==============================================================================

# PITFALL: Don't forget to wrap the .cols part in c()

sw <- 
  starwars |> 
  mutate(
    across(
      .cols = mass, birth_year, 
      .fns = round,
      digits = 1
    )
  ) |> 
  print() # error

# ==============================================================================

# LESSON: To pass arguments to the inner function, add them inside across()

sw <- 
  starwars |> 
  mutate(
    across(
      .cols = c(mass, birth_year), 
      .fns = round,
      digits = 1
    )
  ) |> 
  print()

# ==============================================================================

# USECASE: You can also apply the same summary functions across variables

sw <- 
  starwars |> 
  summarize(
    height = mean(height, na.rm = TRUE),
    mass = mean(mass, na.rm = TRUE),
    birth_year = mean(birth_year, na.rm = TRUE)
  ) |> 
  print()

sw <- 
  starwars |> 
  summarize(
    across(
      .cols = c(height, mass, birth_year), 
      .fns = mean, 
      na.rm = TRUE
    )
  ) |> 
  print()

# SETUP: We will need tidyverse and an example dataset

library(tidyverse)

# Create some example data
dat <- 
  tibble(
    id = c("A_001_01", "A_002_01", "B_001_01", "B_002_01", "C_001_01", "C_002_01"),
    duration = c("01:16", "01:21", "01:49", "00:34", "00:32", "00:54")
  ) |> 
  print()

# ==============================================================================

# USECASE: Separate a column into multiple columns

dat2 <- 
  dat |> 
  separate(
    col = duration, 
    into = c("min", "sec"), 
    sep = ":"
  ) |> 
  print()

# ==============================================================================

# USECASE: This also works with more than two "into" columns

dat2 <- 
  dat |>  
  separate(
    col = id, 
    into = c("group", "subject", "time"), 
    sep = "_"
  ) |> 
  print()

# ==============================================================================

# TIP: To automatically convert strings into numbers, use convert

dat2 <- 
  dat |> 
  separate(
    col = id, 
    into = c("group", "subject", "time"), 
    sep = "_", 
    convert = TRUE
  ) |> 
  print()

# ==============================================================================

# PITFALL: Don't forget to close the "into" vector's parentheses

dat2 <- 
  dat|> 
  separate(col = duration, into = c("min", "sec", sep = ":")) #error

# SETUP: We will need tidyverse and an example dataset

library(tidyverse)

dat2 <- 
  dat|> 
  separate(col = id, into = c("group", "subject", "time"), sep = "x") |> 
  separate(col = duration, into = c("min", "sec"), sep = ":") |> 
  print()

# ==============================================================================

# USECASE: Unite multiple columns into one string

dat3 <- 
  dat2 |> 
  unite(col = "newid", group, subject, time, sep = "-") |> 
  unite(col = "duration", min, sec, sep = ":") |> 
  print()

# ==============================================================================

# LESSON: Retain the columns being united with remove = FALSE

dat3 <- 
  dat2 |> 
  unite(col = "newid", group:time, sep = "", remove = FALSE) |> 
  print()

# SETUP: We will need tidyverse and an example dataset

library(tidyverse)

mpg

# ==============================================================================

# USECASE: Mapping the shape aesthetic to a categorical variable

ggplot(mpg, aes(x = displ, y = hwy, shape = drv)) +
  geom_point(size = 3)

# ==============================================================================

# PITFALL: Don't try to map shape to a continuous variable

ggplot(mpg, aes(x = displ, y = hwy, shape = hwy)) + 
  geom_point() #error

# NOTE: This doesn't work because there are way more numbers than shapes

# ==============================================================================

# LESSON: Color vs. Fill and Size for Blocks

ggplot(mpg, aes(y = class)) + 
  geom_bar()

ggplot(mpg, aes(y = class)) + 
  geom_bar(color = "darkred", fill = "lightblue", size = 1)

# ==============================================================================

# LESSON: Some aesthetics cause grouping when mapped to a categorical variable

ggplot(mpg, aes(x = displ, y = hwy)) + 
  geom_point() + 
  geom_smooth(method = "lm") # single smooth

ggplot(mpg, aes(x = displ, y = hwy, color = drv)) + 
  geom_point() + 
  geom_smooth(method = "lm") # three smooths

# ==============================================================================

# USECASE: Mapping to the fill aesthetic and setting the alpha property

ggplot(mpg, aes(x = hwy, fill = drv)) + 
  geom_density()

ggplot(mpg, aes(x = hwy, fill = drv)) + 
  geom_density(alpha = 0.3)

# ==============================================================================

# TIP: If you map the same variable to multiple aesthetics, you get redundancy

ggplot(mpg, aes(x = displ, y = hwy, shape = drv, color = drv)) +
  geom_point(size = 3) # if color fails, shape still works